© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 9657
    Prev
    Next
    INDEX
    Explanations

    geographical locations and references to places in the context of statistics and demographics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    geographic locations followed by commas and US state abbreviations or country names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.48
    ratislava
    -0.47
    TAWA
    -0.46
    imetsu
    -0.45
    Fiji
    -0.44
    Kerala
    -0.44
     createSprite
    -0.43
     GoogleFonts
    -0.43
    lasi
    -0.43
    asthan
    -0.42
    POSITIVE LOGITS
     USA
    1.88
     America
    1.73
     American
    1.65
     Americans
    1.58
     US
    1.55
    USA
    1.52
     Amerika
    1.50
     Amerikaanse
    1.48
     amerikanischen
    1.47
     США
    1.46
    Activations Density 0.894%

    No Known Activations